We introduce a model called Asset Drivers Framework (ADF), which combines Dimensions Reduction Techniques (DRT) with a ranking procedure to find out assets to be inserted into a financial portfolio. The basic idea is that market securities can be described by a wider number of determinants, but only a few number of them can effectively characterize the assets to form well–balanced portfolios. The ADF manages this as a dimensions reduction problem, and extrapolates for each asset a reduced number of determinants as natural drivers of theirs. The procedure ends by assigning a score to the assets projected in such dimensionally reduced space, with a method of punishment/reward of the way the securities cluster into it. The beauty of the ADF scheme relies on a number of points: (i) it provides a platform to test various dimensions reduction techniques; (ii) looking at the performance, ADF makes possible to build portfolios whose returns are aligned to those of the traditional approach, but with lower variance, and hence lower risk.

A new framework for assets selection based on dimensions reduction techniques

RESTA, MARINA
2011-01-01

Abstract

We introduce a model called Asset Drivers Framework (ADF), which combines Dimensions Reduction Techniques (DRT) with a ranking procedure to find out assets to be inserted into a financial portfolio. The basic idea is that market securities can be described by a wider number of determinants, but only a few number of them can effectively characterize the assets to form well–balanced portfolios. The ADF manages this as a dimensions reduction problem, and extrapolates for each asset a reduced number of determinants as natural drivers of theirs. The procedure ends by assigning a score to the assets projected in such dimensionally reduced space, with a method of punishment/reward of the way the securities cluster into it. The beauty of the ADF scheme relies on a number of points: (i) it provides a platform to test various dimensions reduction techniques; (ii) looking at the performance, ADF makes possible to build portfolios whose returns are aligned to those of the traditional approach, but with lower variance, and hence lower risk.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/312718
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact